Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / DEEPGRAM
Deepgram Nova-3
verified model reference.
Deepgram speech-to-text for recorded meetings, calls, noisy recordings, multilingual utterances and streaming captions.
Not publishedcontext not published
Not publishedmax output
2026-10-12last verified
PRIMARY-SOURCE VERIFIED
Deepgram Nova-3 at a glance.
Deepgram does not publish a token context window for this service. Input modalities: audio. Output: text. Pricing status: Official paid API.
MODEL IDnova-3
CONTEXT WINDOWNot published
MAX OUTPUTNot published
KNOWLEDGE CUTOFFNot published
STANDARD RATE$0.0043per pre-recorded MONOLINGUAL audio minute (streaming/multilingual differ)
OUTPUT RATE—official-paid
CAPABILITY CONTRACT
Published model behavior.
audio
Input modalities come from the cited official model documentation.
text
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Official paid API.
$0.0043 per pre-recorded MONOLINGUAL audio minute (streaming/multilingual differ).
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
What the source record does not assume.
01
Official Pay-As-You-Go pre-recorded monolingual Nova-3 rate is $0.0043 per audio minute; multilingual pre-recorded is $0.0052/minute.
02
Streaming Nova-3 monolingual has a limited-time promotional $0.0048/minute ($0.0077 regular), while multilingual streaming is currently $0.0058/minute ($0.0092 regular). These are separate prices and may change after the promotion.
03
Provider-native model argument model=nova-3 or nova-3-general and available domain options. This record represents general Nova-3, NOT a medical/pharma specialist variant.
04
Optional paid add-ons, multi-channel billing and endpoint type must be verified for true workload costs; only base pre-recorded monolingual audio pricing is displayed.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
Deepgram Nova-3: what changed.
No post-baseline factual changes recorded for Deepgram Nova-3 since 2026-10-12.
VERIFIED BASELINE2026-10-12Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
Deepgram Nova-3 verified history.
Deepgram Nova-3
Baseline verified: context not published · Not published max output · $0.0043 per pre-recorded MONOLINGUAL audio minute (streaming/multilingual differ)
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 77b0ad167e15…
COMPARE DEEPGRAM NOVA-3